:>"^=*@s1dZddlmZddlmZyddlZWn.ek rfddlmZedYnXGddde Z d d Z d d Z d dZ ddZddZddZddZddZddZddddddd Zed!kr-dd"lmZed#ddS)$z8Maximum Entropy code. Uses Improved Iterative Scaling. )print_function)reduceN)MissingPythonDependencyErrorz0Install NumPy if you want to use Bio.MaxEntropy.c@s"eZdZdZddZdS) MaxEntropyaHold information for a Maximum Entropy classifier. Members: classes List of the possible classes of data. alphas List of the weights for each feature. feature_fns List of the feature functions. Car data from example Naive Bayes Classifier example by Eric Meisner November 22, 2003 http://www.inf.u-szeged.hu/~ormandi/teaching >>> from Bio.MaxEntropy import train, classify >>> xcar = [ ... ['Red', 'Sports', 'Domestic'], ... ['Red', 'Sports', 'Domestic'], ... ['Red', 'Sports', 'Domestic'], ... ['Yellow', 'Sports', 'Domestic'], ... ['Yellow', 'Sports', 'Imported'], ... ['Yellow', 'SUV', 'Imported'], ... ['Yellow', 'SUV', 'Imported'], ... ['Yellow', 'SUV', 'Domestic'], ... ['Red', 'SUV', 'Imported'], ... ['Red', 'Sports', 'Imported']] >>> ycar = ['Yes','No','Yes','No','Yes','No','Yes','No','No','Yes'] Requires some rules or features >>> def udf1(ts, cl): ... return ts[0] != 'Red' ... >>> def udf2(ts, cl): ... return ts[1] != 'Sports' ... >>> def udf3(ts, cl): ... return ts[2] != 'Domestic' ... >>> user_functions = [udf1, udf2, udf3] # must be an iterable type >>> xe = train(xcar, ycar, user_functions) >>> for xv, yv in zip(xcar, ycar): ... xc = classify(xe, xv) ... print('Pred: %s gives %s y is %s' % (xv, xc, yv)) ... Pred: ['Red', 'Sports', 'Domestic'] gives No y is Yes Pred: ['Red', 'Sports', 'Domestic'] gives No y is No Pred: ['Red', 'Sports', 'Domestic'] gives No y is Yes Pred: ['Yellow', 'Sports', 'Domestic'] gives No y is No Pred: ['Yellow', 'Sports', 'Imported'] gives No y is Yes Pred: ['Yellow', 'SUV', 'Imported'] gives No y is No Pred: ['Yellow', 'SUV', 'Imported'] gives No y is Yes Pred: ['Yellow', 'SUV', 'Domestic'] gives No y is No Pred: ['Red', 'SUV', 'Imported'] gives No y is No Pred: ['Red', 'Sports', 'Imported'] gives No y is Yes cCsg|_g|_g|_dS)zInitialize the class.N)classesalphas feature_fns)selfr 3/tmp/pip-build-ww9dw3qa/biopython/Bio/MaxEntropy.py__init__Ns  zMaxEntropy.__init__N)__name__ __module__ __qualname____doc__r r r r r rs 4rcCsg}t|jt|jks*txa|jD]V}d}x:t|j|jD]#\}}|||||7}qVW|j|q4W|S)zCalculate the log of the probability for each class. me is a MaxEntropy object that has been trained. observation is a vector representing the observed data. The return value is a list of unnormalized log probabilities for each class. g)lenrrAssertionErrorrzipappend)me observationscoresklassZlprobfnalphar r r calculateUs$"rcCsst||}|d|jd}}xEtdt|D].}|||kr=|||j|}}q=W|S)z%Classify an observation into a class.r)rrranger)rrrZ max_scorerir r r classifyfs rcCswi}xjtt|D]V}xMtt|D]9}|||||}|dkr2||||fEvaluate a feature function on every instance of the training set and class (PRIVATE). fn is a callback function that takes two parameters: a training instance and a class. Return a dictionary of (training set index, class index) -> non-zero value. Values of 0 are not stored in the dictionary. r)rr)rxsrvaluesrjfr r r _eval_feature_fnps r$c six$t|D]\}}||s z+_calc_empirical_expects..r) enumeraterrgetrfloat) r ysrfeaturesindexkeyZys_iexpectNfeaturesrr )r'r _calc_empirical_expectss  $r4c Cst||||}g}xd|D]\}d}x6|jD](\\}} } |||| | 7}q;W|j|t|q"W|S)zCalculate the expectation of each feature from the model (PRIVATE). This is not used in maximum entropy training, but provides a good function for debugging. g)_calc_p_class_given_xitemsrr) r rr-rp_yxZexpectsr2sumrr"r#r r r _calc_model_expectss r9c Cstjt|t|f}t|t|ks?txVt||D]E\}}x6|jD](\\}}} ||||| 7dg|=c sstdtt|kr6td|}} tt|fdd|D} ttt| } t|| | } dgt| } d}x||krpt|| | | | ||}ddt| |D}tt j |d}|} t }| ||_ |_ |_|dk r`||||krPqWtd |S) aFTrain a maximum entropy classifier, returns MaxEntropy object. Train a maximum entropy classifier on a training set. training_set is a list of observations. results is a list of the class assignments for each observation. feature_fns is a list of the features. These are callback functions that take an observation and class and return a 1 or 0. update_fn is a callback function that is called at each training iteration. It is passed a MaxEntropy object that encapsulates the current state of the training. The maximum number of iterations and the convergence criterion for IIS are given by max_iis_iterations and iis_converge, respectively, while max_newton_iterations and newton_converge are the maximum number of iterations and the convergence criterion for Newton's method. zNo data in the training set.z2training_set and results should be parallel lists.cs"g|]}t|qSr )r$)r%r)r training_setr r r(s ztrain..grcSs)g|]\}}tj||qSr )r:rB)r%r>r&r r r r("s NzIIS did not converge) ValueErrorrsortedsetrAr4rKrrr:addrrrrrC)rMresultsrZ update_fnZmax_iis_iterationsZ iis_convergerDrEr r,r-r@rJrrGZnalphasZdiffrr )rrMr trains6          rS__main__) run_doctestverbose)r __future__r functoolsrr: ImportErrorZBiorobjectrrrr$r4r9r5rArIrKrSr Z Bio._utilsrUr r r r  s0 =       =